permission-auditor
Skill1 starsChanged 5 months agoMITView on GitHub
Reviews your .claude/settings.json for overpermissive allowlists, missing denylists, and known-risky tool combos. Suggests safer defaults. Trigger phrases: audit my settings, audit permissions, safer claude, /audit-perms, am I too permissive. Auto-activate the FIRST time the user runs Claude Code in a fresh repo (no .claude/settings.json present) — offer to scaffold a safe default. If any of these are missing, the auditor refuses to skip them:
- Reads credentials
- Deletes or force-pushes
- Commits and pushes
In this repository12 other files it gives its agents.
- commit-curatorSkill
- context-compactorSkill
- cost-trackerSkill
- decision-recorderSkill
- mcp-finderSkill
- prd-builderSkill
- prompt-matcherSkill
- pr-reviewerSkill
- repo-onboarderSkill
- scope-clarifierSkill
- skill-matcherSkill
- tdd-flowSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
No deny on .env, *.key, *.pem, id_rsa*
- Very specific: line 22
No deny on ~/.aws/, ~/.ssh/, ~/.kube/
- Very specific: line 23
No deny on /secrets/
- Distinctive: line 28
No PreToolUse hook to log bash commands
- Distinctive: line 29
No Stop hook (you lose session metadata)
- Very specific: line 30
No safety net for WebFetch to internal URLs
- Very specific: line 63
Read .claude/settings.json (project) and ~/.claude/settings.json (user)
- Distinctive: line 65
Run rule checks above
- Distinctive: line 89
If any of these are missing, the auditor refuses to skip them:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
permission-auditor
Reviews your
.claude/settings.jsonfor overpermissive allowlists, missing denylists, and known-risky tool combos. Suggests safer defaults.
When to activate
Trigger phrases: audit my settings, audit permissions, safer claude, /audit-perms, am I too permissive.
Auto-activate the FIRST time the user runs Claude Code in a fresh repo (no .claude/settings.json present) — offer to scaffold a safe default.
What it checks
Allowlist issues
- Wildcard
Bash(*)— too broad, suggest tightening Bash(rm -rf*)allowed — dangerousBash(curl|wget*)allowed without URL scope — data exfil riskWrite(*)allowed across entire filesystem — should scope to projectEdit(*)outside project root — same
Denylist gaps
- No deny on
.env,*.key,*.pem,id_rsa* - No deny on
~/.aws/,~/.ssh/,~/.kube/ - No deny on
**/secrets/** - No
git push --forcedeny - No
rm -rf /style deny
Hook gaps
- No PreToolUse hook to log bash commands
- No Stop hook (you lose session metadata)
- No safety net for
WebFetchto internal URLs
Output
Permission audit: .claude/settings.json
======================================
Allowlist (8 rules):
✓ Bash(npm install:*) - scoped
✓ Bash(npm run *) - scoped
⚠ Bash(*) - TOO BROAD. Tighten to specific allowed commands.
⚠ Write(*) - no path scope. Limit to project root.
Denylist (2 rules):
⚠ Missing: Read(./.env)
⚠ Missing: Read(./id_rsa*)
⚠ Missing: Bash(git push --force*)
⚠ Missing: Bash(rm -rf /*)
Hooks: none configured.
Recommend at minimum:
- PreToolUse: log Bash commands to a session file
- Stop: sync this conversation to your vault
Suggested patches: (apply with /audit-perms apply)
- Add 4 deny rules above
- Replace Bash(*) with: Bash(npm:*), Bash(git:*), Bash(python:*), Bash(pytest:*)
- Add the two hooksProcess
- Read
.claude/settings.json(project) and~/.claude/settings.json(user) - Parse allow/deny/hook arrays
- Run rule checks above
- Score: 0-100 safety score
- Generate suggested patch as a JSON diff
- Offer to apply
Inputs
- Project
.claude/settings.json - User-level
~/.claude/settings.json - Project file tree (to scope Write/Edit rules)
Outputs
- Audit report (markdown)
- Suggested JSON patch
- One-line summary (e.g. "Safety score: 62/100. 4 issues, 2 critical.")
Slash command
/audit-perms— run the audit/audit-perms apply— apply the suggested patches
Critical issues that block apply
If any of these are missing, the auditor refuses to skip them:
- Deny on
Read(./.env*)andRead(./*.key) - Deny on
Bash(rm -rf /) - Deny on
Bash(git push --force* main)/master
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

